激光与光电子学进展, 2020, 57 (15): 153005, 网络出版: 2020-08-04
基于人工神经网络的水彩笔油墨红外光谱模式识别 下载: 920次
Infrared Spectral Pattern Recognition of Watercolor Pen Ink Based on Artificial Neural Network
红外光谱分析法 水彩笔油墨 人工神经网络 H?lder指数; 模式识别 受试者工作特征(ROC)曲线 infrared spectral analysis method watercolor pen ink artificial neural network H?lder exponent; pattern recognition receiver operating characteristic (ROC) curve
摘要
为实现水彩笔油墨的准确分类,采用红外光谱法对3种品牌15个系列的60个水彩笔油墨样品进行了检验。经过平滑、校正等预处理后,利用均方根误差得到最佳小波变换压缩次数,以达到降低运算复杂度的目的。通过H?lder指数提取出30个样本特征波数,并将其作为输入变量导入人工神经网络的输入层。分配训练集、验证集和测试集对模型进行训练,最终得到该模型的分类正确率为83.3%。最后绘制了受试者工作特征(ROC)曲线,发现第2类样本的分类正确率高于其他两类样本,实现了对水彩笔油墨种类的模式识别。
Abstract
In order to achieve accurate classification of watercolor pen ink, 60 samples of watercolor pen ink from 15 series of 3 brands are tested by infrared spectroscopy in this work. First, after preprocessing such as smoothing and correction, root mean squared error is used to determine the optimal wavelet transform compression times, and the purpose of reducing the complexity of the operation is achieved after compression. Then, H?lder exponent is used to extract 30 characteristic waves of 3 brand samples, which are imported into the input layer of artificial neural network as input variables. The training set, validation set, and test set are assigned to train the model, and the final classification accuracy of the model is 83.3%. Finally, receiver operating characteristic (ROC) curve is drawn, and it is found that the classification accuracy of the second kind of samples is higher than that of the other two types of samples, which realize the pattern recognition of watercolor pen ink types.
王晓宾, 马枭, 王新承. 基于人工神经网络的水彩笔油墨红外光谱模式识别[J]. 激光与光电子学进展, 2020, 57(15): 153005. Xiaobin Wang, Xiao Ma, Xincheng Wang. Infrared Spectral Pattern Recognition of Watercolor Pen Ink Based on Artificial Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(15): 153005.